EP0496902A1 - Système et procédé à base de connaissance pour la recherche de molécules - Google Patents

Système et procédé à base de connaissance pour la recherche de molécules Download PDF

Info

Publication number
EP0496902A1
EP0496902A1 EP91101016A EP91101016A EP0496902A1 EP 0496902 A1 EP0496902 A1 EP 0496902A1 EP 91101016 A EP91101016 A EP 91101016A EP 91101016 A EP91101016 A EP 91101016A EP 0496902 A1 EP0496902 A1 EP 0496902A1
Authority
EP
European Patent Office
Prior art keywords
molecular
matching
molecules
database
similarity
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Withdrawn
Application number
EP91101016A
Other languages
German (de)
English (en)
Inventor
Filippo Fabrocini
Luigi Di Pace
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
IBM Semea SpA
International Business Machines Corp
Original Assignee
IBM Semea SpA
International Business Machines Corp
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by IBM Semea SpA, International Business Machines Corp filed Critical IBM Semea SpA
Priority to EP91101016A priority Critical patent/EP0496902A1/fr
Priority to JP3261950A priority patent/JPH0792804B2/ja
Priority to US07/824,629 priority patent/US5418944A/en
Publication of EP0496902A1 publication Critical patent/EP0496902A1/fr
Withdrawn legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
    • G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
    • G16C20/40—Searching chemical structures or physicochemical data
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y10—TECHNICAL SUBJECTS COVERED BY FORMER USPC
    • Y10S—TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y10S707/00—Data processing: database and file management or data structures
    • Y10S707/99931—Database or file accessing
    • Y10S707/99933—Query processing, i.e. searching
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y10—TECHNICAL SUBJECTS COVERED BY FORMER USPC
    • Y10S—TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y10S707/00—Data processing: database and file management or data structures
    • Y10S707/99941—Database schema or data structure
    • Y10S707/99944—Object-oriented database structure
    • Y10S707/99945—Object-oriented database structure processing

Definitions

  • the invention relates to the Computer Aided Molecular Design (CAMD) field and, more particularly, to those systems and methods that automatically allow the retrieval of molecules previously stored into a molecular database.
  • CAMD Computer Aided Molecular Design
  • the invention relates to a knowledge base molecular retrieval system and method allowing queries for similarity in structure and properties which can be evaluated on whatever molecular substructure in whatever database.
  • the invention makes use of a knowledge base of chemical and physical properties associated with the molecular database. Such a coupling between knowledge base and data base allows to deal with non trivial queries so as to end up in the retrieval of information inaccessible with standard techniques.
  • the molecular design process is generally considered a hard task involving hundreds of experiments needed to synthesize one optimal molecule.
  • chemical and pharmaceutical industries look forward to having new computer tools useful to assist the scientist in such a process.
  • Molecular databases are, among other tools, one of the most widespread.
  • a number of molecular databases are presently available on the market; such databases integrate large amounts of molecules collected from different experimentations.
  • a frequent use of molecular databases consists in retrieving a set of target molecules in some aspect similar to an input one so as to allow the study of such a class of molecules without further experimentations.
  • the invention as claimed is intended to remedy these drawbacks. It solves the problem of scientists who require more powerful molecular retrieval tools, allowing them to make queries in a selective way so as to easily reflect molecular similarity and effectively use the information stored into the database.
  • Another advantage offered by the invention is that the preliminary analysis of molecules and the storing of similarity features into the databases is not needed.
  • the system and method allow to satisfy a number of queries concerning:
  • Figure 1 shows the hardware of the molecular retrieval system which includes a CPU 11 of the general purpose type communicating with a storage 12 containing instructions that control its operation. Moreover, CPU 11 communicates with a storage 13 which contains a knowledge base where a number of chemical and physical properties is associated to a set of molecular fragments. Such fragments have been sorted into three dictionaries: a residue dictionary (the RS-dictionary), a functional group dictionary (the FG-dictionary) and an atom type dictionary (the AT-dictionary). Instruction storage 12 and knowledge base storage 13 may be of the read only storage or random access storage type.
  • CPU 11 is also in communication with a main storage 14 of the random access storage type which is used for storing both the source database 22 and the target database 23 of Figure 2.
  • Input storage 15 is used to store the query entered from a source not shown in Figure 1.
  • Output storage 16 is used to memorize the results of the query.
  • a set of programs manipulates the input query so as to retrieve via similarity matching the searched molecules.
  • the logical architecture of the system is illustrated in Figure 2.
  • Subsystem 2a made of modules 21, 22, 23, 24 will be firstly described.
  • Subsystem 2a is used whenever 8 source database is associated with the retrieval system of the invention here described so as to generate a target database that will be the database effectively utilized during the retrieval process.
  • the generation of the target database 23 must be viewed as a one time only reformulation process.
  • a molecular fragment recognizer module 21 is in communication with both a source database 22 and a target database 23, both stored in a main storage 14. Module 21 also communicates with a knowledge base 24 stored in storage 13.
  • Molecular fragment recognizer 21 analyzes one or more source molecules to generate as output a hierarchical description of the source molecule (see below).
  • Module 22 is a source database, i.e. the database to be associated with the information retrieval system. Molecules, in source database 22, are required to be described in terms of atoms and connectivities.
  • Target database 23 is a database containing a hierarchically representation of each of the molecules stored into source database 22. Such a representation comprises three levels of description: the molecule described in terms of residues, the molecule described in terms of functional groups and the molecule described in terms of atomic entities.
  • Knowledge-base 24 is a dictionary of fragments having associated a number of well known chemical and physical properties. Specifically, the system makes use of a number of dictionaries corresponding to the number of representational levels above described (24a,24b,24c).
  • module 21 reads each of the molecules stored in terms of atomic entities into source database 22. Then, it makes use of RS-dictionary 24a and FG-dictionary 24b embedded into the knowledge base 24 to recognize the corresponding fragments inside the molecule. As a final result, a three level description of each molecule is generated and stored into target database 23. Whenever, during this process, fragments cannot be recognized neither as residues nor as functional groups, the formalization in terms of atomic entities is used to describe the remaining of the molecule.
  • Knowledge base 24 allows the system to accomplish such a step insofar as it allows the system to have a "perception" of the molecules as hierarchical entities with different representations of the molecule associated at each level of the hierarchy.
  • Figure 3 illustrates the hierarchical representation of a molecule obtained after this step.
  • a molecule is described in terms of a graph in which nodes can be or all residues, or all functional groups, or all atoms, and arcs stand for the connectivities between the said molecular fragments.
  • atomic entities are used to represent the molecule at the lower level (the AT-graph); in the following one, the molecule is represented in terms of larger fragments named functional groups such as, for instance, a carboxyl group (the FG-graph); at the next level up, the molecule is described in terms of residues such as, for instance, an amino acid in a peptide (the RS-graph); finally, it is always possible to represent the molecule as a whole with some properties associated to the molecule such as, for instance, the molecular weight.
  • FIG 3 when read from left to right, illustrates firstly the AT-graph, then the FG-graph and, finally, the RS-graph; each circled region is in one-to-one correspondence to the circled region of the next hierarchical level.
  • the hierarchical representation here described is an extension of the representation adopted by the MIDAS database system as presented by T. E. Ferrin et al. in the Journal of Molecular Graphics, vol. 6, March 1988, pp. 1-12.
  • the molecular retrieval process starts when the user interface 28 receives the query to be processed from an input means not shown in Figure 1 (keyboard, magnetic tape reader, diskette drive, etc.).
  • User interface 28 is in communication with a query analyzer 25 for the analysis of the query.
  • Query analyzer 25 is connected with a structural matching module 26 and a model matching module 27.
  • Structural matching module 26 is also connected to a graph matching module 29.
  • Query analyzer 25 is the control module, which selects the appropriate subroutines according to the query type entered into the system.
  • Knowledge base 24 has been partially illustrated during the description of the subsystem 2a.
  • module 24 comprises a number of dictionaries corresponding to the number of representational levels above described.
  • Each dictionary is made of a set of fragments with a number of chemical and physical properties associated to each fragment.
  • the hydroxyl group for instance, appears into FG-dictionary 24b being described as a hydrophilic group with the property of being electron donor.
  • Table 1 Table 2 and Table 3, respectively, are the lists of properties presently being considered into modules 24c, 24b and 24a.
  • Structural matching module 26 and model matching module 27 are both used to test whether there are one or more molecules into target database 23 that satisfy the user query. Each of them is selected according to the query type entered by the user (see below).
  • Graph matching module 29, finally, is a graph matching subroutine used to match molecules described at any level of representation one onto the other.
  • the operation of the subsystem 2b made of modules 24, 25, 26, 27, 28, 29 is here described.
  • a query is entered into module 28, it is processed in order to reformulate it in a standard form (the query statement). Such a step is necessary insofar as the user is normally supposed to enter the query in a graphical mode (see, for instance, Figure 4).
  • the query statement is presented to query analyzer 25 in order to activate the appropriate routines for satisfying the user query.
  • it analyzes the input query to understand the query type.
  • Query analyzer 25, according to the input query will select a number of subroutines implemented to deal with the given query.
  • Module 25 has been designed to deal with four query types. The operation of the retrieval system is described in connection with each query type.
  • the answer to the query is dispatched by query analyzer 25 to user interface 28.

Landscapes

  • Chemical & Material Sciences (AREA)
  • Crystallography & Structural Chemistry (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computing Systems (AREA)
  • Theoretical Computer Science (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
EP91101016A 1991-01-26 1991-01-26 Système et procédé à base de connaissance pour la recherche de molécules Withdrawn EP0496902A1 (fr)

Priority Applications (3)

Application Number Priority Date Filing Date Title
EP91101016A EP0496902A1 (fr) 1991-01-26 1991-01-26 Système et procédé à base de connaissance pour la recherche de molécules
JP3261950A JPH0792804B2 (ja) 1991-01-26 1991-10-09 分子検索方法およびシステム
US07/824,629 US5418944A (en) 1991-01-26 1992-01-23 Knowledge-based molecular retrieval system and method using a hierarchy of molecular structures in the knowledge base

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
EP91101016A EP0496902A1 (fr) 1991-01-26 1991-01-26 Système et procédé à base de connaissance pour la recherche de molécules
US07/824,629 US5418944A (en) 1991-01-26 1992-01-23 Knowledge-based molecular retrieval system and method using a hierarchy of molecular structures in the knowledge base

Publications (1)

Publication Number Publication Date
EP0496902A1 true EP0496902A1 (fr) 1992-08-05

Family

ID=26128699

Family Applications (1)

Application Number Title Priority Date Filing Date
EP91101016A Withdrawn EP0496902A1 (fr) 1991-01-26 1991-01-26 Système et procédé à base de connaissance pour la recherche de molécules

Country Status (3)

Country Link
US (1) US5418944A (fr)
EP (1) EP0496902A1 (fr)
JP (1) JPH0792804B2 (fr)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO1997014106A1 (fr) * 1995-10-13 1997-04-17 Terrapin Technologies, Inc. Identification d'activite chimique commune par comparaison de fragments substructuraux
WO1999035599A1 (fr) * 1998-01-09 1999-07-15 Everett, Richard, Stephen, Hans Dispositif et procede utilises dans la production de composes chimiques
WO2002041179A2 (fr) * 2000-11-17 2002-05-23 Amedis Pharmaceuticals Limited Procede de generation d'une base de donnees de fragments moleculaires

Families Citing this family (55)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5995908A (en) * 1990-09-20 1999-11-30 Margaret I. Pullen Integrated field modeling system
US5615112A (en) * 1993-01-29 1997-03-25 Arizona Board Of Regents Synthesized object-oriented entity-relationship (SOOER) model for coupled knowledge-base/database of image retrieval expert system (IRES)
US5577239A (en) * 1994-08-10 1996-11-19 Moore; Jeffrey Chemical structure storage, searching and retrieval system
US5657255C1 (en) * 1995-04-14 2002-06-11 Interleukin Genetics Inc Hierarchic biological modelling system and method
US5752019A (en) * 1995-12-22 1998-05-12 International Business Machines Corporation System and method for confirmationally-flexible molecular identification
WO1997027559A1 (fr) 1996-01-26 1997-07-31 Patterson David E Procede pour creer une bibliotheque moleculaire virtuelle et procede pour y faire des recherches, en utilisant des descripteurs valides de structure moleculaire
US6185506B1 (en) * 1996-01-26 2001-02-06 Tripos, Inc. Method for selecting an optimally diverse library of small molecules based on validated molecular structural descriptors
US5880972A (en) * 1996-02-26 1999-03-09 Pharmacopeia, Inc. Method and apparatus for generating and representing combinatorial chemistry libraries
US5989835A (en) 1997-02-27 1999-11-23 Cellomics, Inc. System for cell-based screening
US5751605A (en) * 1996-08-15 1998-05-12 Tripos, Inc. Molecular hologram QSAR
US6189013B1 (en) 1996-12-12 2001-02-13 Incyte Genomics, Inc. Project-based full length biomolecular sequence database
US6023659A (en) * 1996-10-10 2000-02-08 Incyte Pharmaceuticals, Inc. Database system employing protein function hierarchies for viewing biomolecular sequence data
US6519583B1 (en) 1997-05-15 2003-02-11 Incyte Pharmaceuticals, Inc. Graphical viewer for biomolecular sequence data
JPH10221728A (ja) * 1997-02-07 1998-08-21 Canon Inc ぶれ補正光学手段付きレンズ鏡筒
WO1998047087A1 (fr) * 1997-04-17 1998-10-22 Glaxo Group Ltd. Deconvolution statistique de melanges
US6611828B1 (en) 1997-05-15 2003-08-26 Incyte Genomics, Inc. Graphical viewer for biomolecular sequence data
US6182016B1 (en) 1997-08-22 2001-01-30 Jie Liang Molecular classification for property prediction
CA2308115A1 (fr) * 1997-10-24 1999-05-06 University Of Utah Research Foundation Interaction de peptides d'alpha-conotoxine avec des recepteurs neuraux d'acetylcholine nicotinique
US6051029A (en) * 1997-10-31 2000-04-18 Entelos, Inc. Method of generating a display for a dynamic simulation model utilizing node and link representations
US6078739A (en) * 1997-11-25 2000-06-20 Entelos, Inc. Method of managing objects and parameter values associated with the objects within a simulation model
US6069629A (en) * 1997-11-25 2000-05-30 Entelos, Inc. Method of providing access to object parameters within a simulation model
US6408308B1 (en) * 1998-01-29 2002-06-18 Incyte Pharmaceuticals, Inc. System and method for generating, analyzing and storing normalized expression datasets from raw expression datasets derived from microarray includes nucleic acid probe sequences
AU5096499A (en) * 1998-07-13 2000-02-01 Glaxo Group Limited Chemical compound information system
US6654736B1 (en) * 1998-11-09 2003-11-25 The United States Of America As Represented By The Secretary Of The Army Chemical information systems
JP2002530748A (ja) * 1998-11-13 2002-09-17 セロミックス インコーポレイテッド 実験データを効率的に収集して記憶するための方法及びシステム
US6434545B1 (en) 1998-12-16 2002-08-13 Microsoft Corporation Graphical query analyzer
US6323852B1 (en) * 1999-01-04 2001-11-27 Leadscope, Inc. Method of analyzing organizing and visualizing chemical data with feature hierarchy
US7912689B1 (en) 1999-02-11 2011-03-22 Cambridgesoft Corporation Enhancing structure diagram generation through use of symmetry
US7295931B1 (en) * 1999-02-18 2007-11-13 Cambridgesoft Corporation Deriving fixed bond information
US7219020B1 (en) 1999-04-09 2007-05-15 Axontologic, Inc. Chemical structure similarity ranking system and computer-implemented method for same
AU4216400A (en) * 1999-04-09 2000-11-14 Merck & Co., Inc. Chemical structure similarity ranking system and computer-implemented method forsame
WO2000063793A2 (fr) * 1999-04-16 2000-10-26 Entelos, Inc. Procede et appareil pour effectuer des operations de simulation liees a l'aide d'un modele de systeme informatise
US6665685B1 (en) * 1999-11-01 2003-12-16 Cambridge Soft Corporation Deriving database interaction software
WO2001055951A2 (fr) 2000-01-25 2001-08-02 Cellomics, Inc. Procede et systeme de creation d'inferences automatisees des connaissances d'interaction physico-chimiques provenant de bases de donnees de donnees de co-occurrences
US6907350B2 (en) * 2000-03-13 2005-06-14 Chugai Seiyaku Kabushiki Kaisha Method, system and apparatus for handling information on chemical substances
US7272509B1 (en) * 2000-05-05 2007-09-18 Cambridgesoft Corporation Managing product information
US7356419B1 (en) 2000-05-05 2008-04-08 Cambridgesoft Corporation Deriving product information
DE10043853A1 (de) * 2000-09-06 2002-03-14 Merck Patent Gmbh Verfahren zur Erstellung von Synthesepfaden
US6813615B1 (en) 2000-09-06 2004-11-02 Cellomics, Inc. Method and system for interpreting and validating experimental data with automated reasoning
US7330793B2 (en) * 2001-04-02 2008-02-12 Cramer Richard D Method for searching heterogeneous compound databases using topomeric shape descriptors and pharmacophoric features
US7155453B2 (en) * 2002-05-22 2006-12-26 Agilent Technologies, Inc. Biotechnology information naming system
KR20030019681A (ko) * 2001-08-29 2003-03-07 바이오인포메틱스 주식회사 웹 기반 프로테옴 분석 및 관리 시스템 및 그 방법
AUPR981002A0 (en) * 2002-01-02 2002-01-31 Proteome Systems Ltd 2 Dimensional structure queries
EP1721268A1 (fr) * 2004-03-05 2006-11-15 Applied Research Systems ARS Holding N.V. Procede de recherche rapide dans des substructure de bibliotheques chimiques non enumerees
US20060053172A1 (en) * 2004-09-03 2006-03-09 Biowisdom Limited System and method for creating, editing, and using multi-relational ontologies
US20060053174A1 (en) * 2004-09-03 2006-03-09 Bio Wisdom Limited System and method for data extraction and management in multi-relational ontology creation
US20060053173A1 (en) * 2004-09-03 2006-03-09 Biowisdom Limited System and method for support of chemical data within multi-relational ontologies
US20060053175A1 (en) * 2004-09-03 2006-03-09 Biowisdom Limited System and method for creating, editing, and utilizing one or more rules for multi-relational ontology creation and maintenance
US7496593B2 (en) 2004-09-03 2009-02-24 Biowisdom Limited Creating a multi-relational ontology having a predetermined structure
US20060053171A1 (en) * 2004-09-03 2006-03-09 Biowisdom Limited System and method for curating one or more multi-relational ontologies
US20060053382A1 (en) * 2004-09-03 2006-03-09 Biowisdom Limited System and method for facilitating user interaction with multi-relational ontologies
US20060074833A1 (en) * 2004-09-03 2006-04-06 Biowisdom Limited System and method for notifying users of changes in multi-relational ontologies
US7505989B2 (en) 2004-09-03 2009-03-17 Biowisdom Limited System and method for creating customized ontologies
US7493333B2 (en) * 2004-09-03 2009-02-17 Biowisdom Limited System and method for parsing and/or exporting data from one or more multi-relational ontologies
US20090228445A1 (en) * 2008-03-04 2009-09-10 Systems Biology (1) Pvt. Ltd. Automated molecular mining and activity prediction using xml schema, xml queries, rule inference and rule engines

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS60107554A (ja) * 1983-11-16 1985-06-13 Ube Ind Ltd 未知物質の化学構造を決定する方法および装置
US4642762A (en) * 1984-05-25 1987-02-10 American Chemical Society Storage and retrieval of generic chemical structure representations
JPS61223941A (ja) * 1985-03-29 1986-10-04 Kagaku Joho Kyokai 化学構造の検索方法

Non-Patent Citations (4)

* Cited by examiner, † Cited by third party
Title
COMMUNICATIONS OF THE ASSOCIATION FOR COMPUTING MACHINERY. vol. 30, no. 11, November 1987, NEW YORK US pages 909 - 921; Richard H. Lathrop et al: "Ariadne: Pattern-directed Inference and Hierarchical Abstraction in Protein Structure Recognition" *
EXPERT SYSTEMS. vol. 6, no. 3, August 1989, OXFORD, GB pages 144 - 156; John A. Brugge et al: "Evolution of a knowledge-based system for determining structural components of proteins" *
Journal of Molecular Graphics vol. 6, no. 1, March 1988, pages 2 - 12; T.E.Ferrin et al: "The Midas Database System" *
PARALLEL COMPUTING. vol. 8, no. 1-3, October 1988, AMSTERDAM NL pages 399 - 407; C.A. Pogue et al: "Searching and clustering of databases using the ICL Distributed Array Processor" *

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO1997014106A1 (fr) * 1995-10-13 1997-04-17 Terrapin Technologies, Inc. Identification d'activite chimique commune par comparaison de fragments substructuraux
WO1999035599A1 (fr) * 1998-01-09 1999-07-15 Everett, Richard, Stephen, Hans Dispositif et procede utilises dans la production de composes chimiques
WO2002041179A2 (fr) * 2000-11-17 2002-05-23 Amedis Pharmaceuticals Limited Procede de generation d'une base de donnees de fragments moleculaires
WO2002041179A3 (fr) * 2000-11-17 2004-05-21 Amedis Pharm Ltd Procede de generation d'une base de donnees de fragments moleculaires

Also Published As

Publication number Publication date
JPH0628409A (ja) 1994-02-04
US5418944A (en) 1995-05-23
JPH0792804B2 (ja) 1995-10-09

Similar Documents

Publication Publication Date Title
EP0496902A1 (fr) Système et procédé à base de connaissance pour la recherche de molécules
McArdle et al. Using multivariate data to structure developmental change
US6574624B1 (en) Automatic topic identification and switch for natural language search of textual document collections
Ferhatosmanoglu et al. Approximate nearest neighbor searching in multimedia databases
US6199061B1 (en) Method and apparatus for providing dynamic help topic titles to a user
US8024331B2 (en) Construction of trainable semantic vectors and clustering, classification, and searching using trainable semantic vectors
US7177798B2 (en) Natural language interface using constrained intermediate dictionary of results
Cardie A case-based approach to knowledge acquisition for domain-specific sentence analysis
US5696964A (en) Multimedia database retrieval system which maintains a posterior probability distribution that each item in the database is a target of a search
US5463773A (en) Building of a document classification tree by recursive optimization of keyword selection function
US5787274A (en) Data mining method and system for generating a decision tree classifier for data records based on a minimum description length (MDL) and presorting of records
US5404507A (en) Apparatus and method for finding records in a database by formulating a query using equivalent terms which correspond to terms in the input query
US20030225757A1 (en) Displaying portions of text from multiple documents over multiple database related to a search query in a computer network
US6112204A (en) Method and apparatus using run length encoding to evaluate a database
De Soete et al. Optimal variable weighting for hierarchical clustering: an alternating least-squares algorithm
US6643642B1 (en) Hierarchical mapped database system for identifying searchable terms associated with data nodes
Lee et al. Indexing for complex queries on a query-by-content image database
EP1099171A2 (fr) Index pour une base de donnees semi-structuree
Buckland et al. Expertise, task complexity, and artificial intelligence: A conceptual framework
WO2000049527A1 (fr) Moteur de mise en correspondance
JPH1185492A (ja) オブジェクト指向データモデル作成支援装置
Conklin et al. Knowledge discovery in molecular databases
Becks Visual knowledge management with adaptable document maps
Nguyen et al. Knowledge discovery by rough set methods
US6629088B1 (en) Method and apparatus for measuring the quality of descriptors and description schemes

Legal Events

Date Code Title Description
PUAI Public reference made under article 153(3) epc to a published international application that has entered the european phase

Free format text: ORIGINAL CODE: 0009012

AK Designated contracting states

Kind code of ref document: A1

Designated state(s): DE FR GB IT

17P Request for examination filed

Effective date: 19921119

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: THE APPLICATION HAS BEEN WITHDRAWN

18W Application withdrawn

Withdrawal date: 19951127